jupyter编程,更改为pytho脚本请自行修改。整体基于李沐老师的动手学习深度学习-pytorch 2021版。下面是个人模仿代码和笔记,主要用于个人复习,如有错误请告知。
Fashion-MNIST:替代MNIST手写数字集的图像数据集
导入包
%matplotlib inline
import torch
import torchvision
from torch.utils import data
from torchvision import transforms
import matplotlib.pyplot as plt
from d2l import torch as d2l
下载或导入数据:
trans = transforms.ToTensor()
mnist_train = torchvision.datasets.FashionMNIST(
root='./data',
train = True,
transform = trans,
download = True,
)
mnist_test = torchvision.datasets.FashionMNIST(
root='./data',
train = False,
transform = trans,
download = True,
)
可视化数据(沐神有提供其他的绘图脚本,但我自己写了一个简单的)
def get_fashion_mnist_labels(labels): #@save
"""返回Fashion-MNIST数据集的文本标签。"""
text_labels = [
't-shirt', 'trouser', 'pullover', 'dress', 'coat', 'sandal', 'shirt',
'sneaker', 'bag', 'ankle boot']
return text_labels[int(labels)]
fig, ax = plt.subplots(
nrows=3,
ncols=4,
sharex=True,
sharey=True, )
ax = ax.flatten()
for i in range(12):
# 只查看了前面12张图片
img = mnist_train.data[i]
ax[i].imshow(img)
ax[i].set(title=get_fashion_mnist_labels(mnist_train[i][1]))
ax[0].set_xticks([])
ax[0].set_yticks([])
plt.tight_layout()
plt.show()
batch_size = 256
def get_dataloader_workers():
"""使用四个进程读取数据"""
return 4
train_iter = data.DataLoader(mnist_train,batch_size,shuffle=True,
num_workers=get_dataloader_workers())
def load_data_fashion_mnist(batch_size,resize=None):
"""下载Fashion-MNIST数据集,并将其保存至内存中"""
trans = [transforms.ToTensor()]
if resize:
trans.insert(0,transforms.Resize(resize)) # transforms.Resize将图片最小的一条边缩放到指定大小,另一边缩放对应比例
trans = transforms.Compose(trans) # compose用于串联多个操作
mnist_train = torchvision.datasets.FashionMNIST(root="./data",
train=True,
transform=trans,
download=True)
mnist_test = torchvision.datasets.FashionMNIST(root="./data",
train=False,
transform=trans,
download=True)
return (data.DataLoader(mnist_train,batch_size,shuffle=True,
num_workers=get_dataloader_workers()),
data.DataLoader(mnist_test,batch_size,shuffle=True,
num_workers = get_dataloader_workers()))
import torch
from IPython import display
from d2l import torch as d2l
batch_size = 256
train_iter,test_iter = load_data_fashion_mnist(batch_size)
num_inputs = 784 #图片大小为28*28
num_outputs = 10 # 分为10类
W = torch.normal(0, 0.01, size=(num_inputs, num_outputs), requires_grad=True) # 初始化权重
b = torch.zeros(num_outputs, requires_grad=True) # 初始偏置为0
def softmax(X):
"""softmax函数"""
X_exp = torch.exp(X)
partition = X_exp.sum(1,keepdim=True) # 按行求和,得一列
return X_exp/partition
def net(X):
return softmax(torch.matmul(X.reshape((-1,W.shape[0])),W)+b)
def cross_entropy(y_hat,y):
return -torch.log(y_hat[range(len(y_hat)),y])
def updater(batch_size):
"""sgd 小批量梯度下降更新"""
return d2l.sgd([W, b], lr, batch_size)
def train_epoch(net, train_iter, loss, updater): #@save
"""训练模型一个迭代周期"""
# 将模型设置为训练模式
if isinstance(net, torch.nn.Module):
net.train()
# 训练损失总和、训练准确度总和、样本数
metric = Accumulator(3)
for X, y in train_iter:
# 计算梯度并更新参数
y_hat = net(X)
l = loss(y_hat, y)
if isinstance(updater, torch.optim.Optimizer):
# 使用PyTorch内置的优化器和损失函数
updater.zero_grad()
l.backward()
updater.step()
metric.add(
float(l) * len(y), accuracy(y_hat, y),
y.size().numel())
else:
# 使用定制的优化器和损失函数
l.sum().backward()
updater(X.shape[0])
metric.add(float(l.sum()), accuracy(y_hat, y), y.numel())
# 返回训练损失和训练准确率
return metric[0] / metric[2], metric[1] / metric[2]
def train(net, train_iter, test_iter, loss, num_epochs, updater): #@save
"""训练模型"""
animator = Animator(xlabel='epoch', xlim=[1, num_epochs], ylim=[0.3, 0.9],
legend=['train loss', 'train acc', 'test acc'])
for epoch in range(num_epochs):
train_metrics = train_epoch(net, train_iter, loss, updater)
test_acc = evaluate_accuracy(net, test_iter)
animator.add(epoch + 1, train_metrics + (test_acc,))
train_loss, train_acc = train_metrics
assert train_loss < 0.5, train_loss
assert train_acc <= 1 and train_acc > 0.7, train_acc
assert test_acc <= 1 and test_acc > 0.7, test_acc
lr = 0.1
num_epochs = 100
train(net, train_iter, test_iter, cross_entropy, num_epochs, updater)
def predict(net, test_iter, n=6): #@save
"""预测标签"""
for X, y in test_iter:
break
trues = d2l.get_fashion_mnist_labels(y)
preds = d2l.get_fashion_mnist_labels(net(X).argmax(axis=1))
titles = [true + '\n' + pred for true, pred in zip(trues, preds)]
d2l.show_images(X[0:n].reshape((n, 28, 28)), 1, n, titles=titles[0:n])
predict(net, test_iter)
import torch
from torch import nn
from d2l import torch as d2l
# 根据批次加载数据,可以使用d2l中的函数,也可以使用上面自定义的
batch_size = 256
train_iter,test_iter = load_data_fashion_mnist(batch_size)
# 定义网络模型
net = nn.Sequential(nn.Flatten(),nn.Linear(784,10))
def init_weights(m):
if type(m) == nn.Linear:
nn.init.normal_(m.weight,std=0.01)
net.apply(init_weights)
# 定义损失函数
loss = nn.CrossEntropyLoss()
# 定义梯度更新函数
trainer = torch.optim.SGD(net.parameters(),lr=0.01)
# 训练数据
num_epochs = 100
d2l.train_ch3(net,train_iter,test_iter,loss,num_epochs,trainer)